pragmatic_segmenter 0.1.7 → 0.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ac7a7ecd4d02a9d2df378b3c174ba338238b26df
-  data.tar.gz: fa33b3bd39e88c065bef560f0d22b3124ed99da8
+  metadata.gz: 1708727dc62734ca577e6d9b1c05af49551563a7
+  data.tar.gz: 1f00d14609486e72068d3a189851ef9fd9f66a31
 SHA512:
-  metadata.gz: ff3c13ce3db23f80d2051fe95b94dc7dd057ed36818f06b6ddff18f14179be88ef0d381250d1bebba3322b5439d59658522fb56440fb082fb69d32baefb54e7b
-  data.tar.gz: 21b0f050be65715cf1ab020d7ec31780369ef6cb64a6de0ff18176eabd94e5a38073f57ed258bb21c62c1d8eaf4978a6cb66e1e4f10c697549fb319dc762b02c
+  metadata.gz: 9a45479d6c2cfa930e2d6bafcaf9648208dee53f79b5d16fa020fe5427210c3b7673663707bf1feda98344fe4765796a060fac8055f2641f107d7d1ce5e51022
+  data.tar.gz: c92f8ee9fb924a3b8e46d6efb1fa9fa27eb72a06a66f9e9d64f84efa4458efd42a6d88d63f4c28880cd7ada18f333cd8ab927bb9a580d319d1ff1ec38e3b3664

data/README.md

@@ -769,7 +769,10 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.1.7**  
 * Add Alice in Wonderland specs  
 * Fix parenthesis between double quotations bug  
-* Fix split after quotation ending in dash bug      
+* Fix split after quotation ending in dash bug  
+
+**Version 0.1.8**  
+* Fix bug in splitting new sentence after single quotes  
 
 ## Contributing
 

data/lib/pragmatic_segmenter/between_punctuation.rb

@@ -49,7 +49,8 @@ module PragmaticSegmenter
     def sub_punctuation_between_single_quotes(txt)
       PragmaticSegmenter::PunctuationReplacer.new(
         matches_array: txt.scan(BETWEEN_SINGLE_QUOTES_REGEX),
-        text: txt
+        text: txt,
+        match_type: 'single'
       ).replace
     end
 

data/lib/pragmatic_segmenter/punctuation_replacer.rb

@@ -4,11 +4,15 @@ module PragmaticSegmenter
   # This class replaces punctuation that is typically a sentence boundary
   # but in this case is not a sentence boundary.
   class PunctuationReplacer
+    # Rubular: http://rubular.com/r/2YFrKWQUYi
+    BETWEEN_SINGLE_QUOTES_REGEX = /(?<=\s)'(?:[^']|'[a-zA-Z])*'/
+
     include Rules
-    attr_reader :matches_array, :text
-    def initialize(text:, matches_array:)
+    attr_reader :matches_array, :text, :match_type
+    def initialize(text:, matches_array:, **args)
       @text = text
       @matches_array = matches_array
+      @match_type = args[:match_type]
     end
 
     def replace
@@ -29,7 +33,9 @@ module PragmaticSegmenter
         sub_4 = sub_characters(txt, sub_3, '!', '&ᓴ&')
         sub_5 = sub_characters(txt, sub_4, '?', '&ᓷ&')
         sub_6 = sub_characters(txt, sub_5, '？', '&ᓸ&')
-        sub_7 = sub_characters(txt, sub_6, "'", '&⎋&')
+        unless match_type.eql?('single')
+          sub_7 = sub_characters(txt, sub_6, "'", '&⎋&')
+        end
       end
       txt.apply(SubEscapedRegexReservedCharacters::All)
     end

data/lib/pragmatic_segmenter/version.rb

@@ -1,3 +1,3 @@
 module PragmaticSegmenter
-  VERSION = "0.1.7"
+  VERSION = "0.1.8"
 end

data/spec/pragmatic_segmenter_spec.rb

@@ -1498,6 +1498,11 @@ RSpec.describe PragmaticSegmenter::Segmenter do
         ps = PragmaticSegmenter::Segmenter.new(text: "\"Dinah'll miss me very much to-night, I should think!\" (Dinah was the cat.) \"I hope they'll remember her saucer of milk at tea-time. Dinah, my dear, I wish you were down here with me!\"")
         expect(ps.segment).to eq(["\"Dinah'll miss me very much to-night, I should think!\"", "(Dinah was the cat.)", "\"I hope they'll remember her saucer of milk at tea-time. Dinah, my dear, I wish you were down here with me!\""])
       end
+
+      it "correctly segments text #098" do
+        ps = PragmaticSegmenter::Segmenter.new(text: "Hello. 'This is a test of single quotes.' A new sentence.")
+        expect(ps.segment).to eq(["Hello.", "'This is a test of single quotes.'", "A new sentence."])
+      end
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.8
 platform: ruby
 authors:
 - Kevin S. Dias